AI KYB Merchant ScreeningAdverse Media — Negative News Sentiment
Prototype engines onlineResidency: Indonesia profile+ New Screening
KSI
Module 4 · Adverse Media

Adverse Media — Negative News Sentiment

Search negative news related to merchant companies and relevant individuals, including crime, financial crime, corruption, insolvency and sanctions-related issues.

← Modules
RFI module deep-dive

Adverse Media — Negative News Sentiment

Prototype page exposes input contracts, processing stages, structured outputs, quality controls, privacy controls, integration points, PoC questions and evidence needed before production acceptance.

Open PoC Benchmark Lab

Inputs

Merchant legal nameNormalized company name and aliases
IndividualsDirectors, beneficial owners / officers as authorized for screening
IdentifiersLocation, DOB or other lawful disambiguators where necessary
Risk taxonomyFraud, corruption, criminal, bankruptcy, sanctions, etc.

Processing Pipeline

Query expansion

Generate controlled name variants and business aliases.

Source retrieval

Search licensed/approved local and international sources; record source provenance.

Entity resolution

Score subject match using name, organization, location, role, dates and other allowed features.

Deduplication

Cluster syndicated articles and remove duplicate evidence.

Issue classification

Classify issue type, severity, allegation vs confirmed outcome, and recency.

Human review gate

Ambiguous or high-impact findings must be dispositioned by an analyst before final decision.

Structured Outputs

candidate_hitsArticle / subject candidates
entity_scoreEntity match confidence
issue_typeFraud / corruption / criminal / insolvency / sanction
statusAllegation / investigation / judgment / sanction etc.
relevanceRank and recency
auditSource, timestamp, disposition and reviewer
Local + international adverse mediaSearch negative coverage relevant to merchant and related individuals from approved media sources.
Risk categorizationClassify fraud, corruption, criminal, bankruptcy/insolvency, sanctions and other configured risk issues.
Entity resolutionDifferentiate persons/entities with common names and reduce false positives.
Deduplication & relevance rankingCollapse syndicated/duplicate articles and rank findings by relevance.
PEP / sanctions linkageLink findings with PEP/sanctions screening context including domestic lists such as DTTOT and DPPSPM where integrated.
Audit evidenceRetain source reference, publication date, retrieval time, entity score and analyst disposition.
#Question to providerPrototype statusEvidence / response expected
1What media-source coverage is monitored and how real-time is the refresh?PoC responseProvide source inventory, Indonesia/international coverage, refresh SLAs and licensing.
2How does entity resolution reduce false positives for common names?PoC responseProvide matching features, thresholds, test results and manual-review controls.
3Is the solution integrated with PEP/sanctions screening and how are domestic lists handled?PoC responseShow connectors, list-update process, matching logic and governance.
4Is an audit trail and source reference available for each finding?PoC responseShow evidence object and decision lineage.
5How is Bahasa Indonesia content supported?PoC responseProvide language benchmark and local-name/entity handling.

High-impact matching

False-positive protection is critical because adverse-media errors can unfairly block onboarding.

Special / criminal data

Where processing involves criminal or other sensitive data, purpose, necessity, access and retention require stronger controls.

Allegation ≠ fact

UI must explicitly distinguish allegation, investigation, charge, judgment and sanction status.

Correction / dispute

Merchant can trigger review of incorrect identity matches or stale/incorrect evidence.

Illustrative structured output

Schema is intentionally explicit to support decision-engine integration, explainability and audit. Values are simulated.

{ "module":"adverse_media", "subject":{"type":"company","name":"PT Contoh"}, "hits":[{ "issue":"fraud_allegation", "entity_match":0.71, "relevance":0.82, "publication_date":"2026-05-03", "source_ref":"EV-MEDIA-883", "status":"manual_review_required" }], "pep_sanction_context":{"screened":true,"material_hit":false} }